Live data from Hacker News

Viewing profile — seahyinghang8

seahyinghang8

HN member
Joined
Sun, Sep 16, 2018, 4:54 PM UTC
HN karma
66
Public activity
25 items

About seahyinghang8

No profile information was provided.

Recent public activity

  1. comment
    Comment #49191681

    founder of castform here, we believe that as agent deployment moves from experimentation phase where cost doesn't matter as much to deployment (what's the margin of serving the req…

  2. comment
    Comment #49191646

    tldr: we generated synthetic training questions from the gitlab product handbook. totally agree that this larger corpus with harder to search information would be a good way to str…

  3. comment
    Comment #49191622

    we actually have the test benchmark against luna but no deepseek flash (we haven't added DSFlash into our benchmarking model pipeline) you can check out the full comparison against…

  4. comment
    Comment #49191603

    founder of castform here again - slightly unrelated to retrieval but on the topic that folks are discussing here, i was actually collecting benchmarking various coding traces for t…

  5. comment
    Comment #49191576

    we actually have the test benchmark against luna too! it's just not in our title but you can see it in the first diagram below the title. luna does pretty well tbh but sol is just …

  6. comment
    Comment #49191513

    (founder of castform here) - we didn't get to dive too deep into the dataset we were using for the retrieval in the blogpost for brevity, but we did link the training run (which sh…

  7. comment
    Comment #49191436

    (founder of castform here!) - having worked at FAANG / big tech, i totally get this. our example was on gitlab's open source company handbook but i think a real company's corpus is…

  8. comment
    Comment #48270209

    i really hope that's the case

  9. comment
    Comment #48142276

    you should check out https://openai.com/index/gpt-5-5-bio-bug-bounty/

  10. comment
    Comment #48067984

    i use zed 1.0 agent interface and it's pretty great. cool to see that pokegent is modeled after zed's ACP. tho zed has been bugging out recently where the agents just stop working …

  11. comment
    Comment #41880234

    Xcode 16 recently released swift predictive completion but it requires ARM processor with more than 8GB memory. We made an Xcode "extension" that provides AI completion that works …

  12. story
  13. comment
    Comment #39294048

    gamma is lagging on ios safari...

  14. comment
    Comment #38478571

    This project was inspired from our jobs where we spent time writing technical documentation on the stuff that we've built. We'd thought it would be cool if GPT4-V could automatical…

  15. story
  16. story
  17. comment
    Comment #38385696

    Oh I did not make it, here is the link to whom I believe to be the creator: https://github.com/copy/ I discovered it while browsing the web and thought it'd be interesting to share…

  18. story
  19. story
  20. comment
    Comment #37436544

    Hey HN! We're excited to introduce Charty AI, our attempt to change the way we think about and create data dashboards. Creating dashboards is a time-consuming endeavor, especially …

  21. story
  22. comment
    Comment #35605553

    Inspired by Jupyterlite and GPT, I've build an IPython notebook that runs completely in your browser with Pyodide, with a GPT copilot, as part of Svelte's hackathon. The chat inter…

  23. story
  24. comment
    Comment #31022007

    Hey HN! We made this extension that lets you run any python code on the web by using Pyodide. You can try it by installing this VSCode extension on GitHub.dev / VSCode.dev. Since i…

  25. story
    Show HN: Run Python code on GitHub.dev with zero-setup

    We made this extension that lets you run any python code on the web by using Pyodide. You can try it by installing this VSCode extension on GitHub.dev / VSCode.dev. Since it is usi…